Search

In the milling process, the wear area of the tool is often segmented using the traditional image processing method to quantify the tool wear value. However, these methods have the disadvantages of having weak anti-noise capabilities and low segmentation accuracy. Although the semantic segmentation network can achieve excellent segmentation accuracy, obtaining enough end mill wear images to support the semantic segmentation network's training is challenging due to the high acquisition cost of wear images. As a result, this paper suggests a small sample end mill wear area segmentation method based on transfer learning and generative adversarial networks to address the issue of insufficient samples of end mill wear images. In this paper, WGAN is used to generate wear images to expand the dataset with a few samples, and the transfer learning method is used to improve the generalization ability of the segmentation network and finally achieve small sample training. This approach increases mPA by 4.46% and mIOU by 8.97% when compared to merely using the semantic segmentation network for small sample training. According to experimental findings, this method not only has high stability and segmentation accuracy but also solves the problem of insufficient end mill wear image samples. The method proposed in this paper can be effectively applied to the intelligent detection of the tool wear state, improving the accuracy and stability of the measurement of the tool wear value. [ABSTRACT FROM AUTHOR]

This paper aims to present a predicted force model of vibration-assisted broaching (VAB). Based on the geometric features and kinetic characteristics of broach, the model focuses on three important points: (i) the cutting force of single tooth, (ii) the number of teeth in contact with the workpiece, and (iii) the influence of simple harmonic motion (SHM). Firstly, according to the empirical approach (EA) and the shear angle (SA) theory, two kinds of single-tooth model of broaching are built. Secondly, considering the length of cutting edge and the number of cutting tooth, two multi-tooth models based on the single-tooth models are presented. Then, with the influence of broach motion, the models of VAB force are finally established. Verification experiments are conducted for the developed force model and show that the calculated results of SA model are more agreeing well with the experimental values when vibration frequency increased. In addition, the VAB model is helpful in the application of vibration broaching. [ABSTRACT FROM AUTHOR]

Complex profile broaches are widely used in the manufacture of complex parts of aero-engines, but the forces in the broaching process are difficult to predict and control. A new numerical model for broaching force with complex profile tools was presented, which considered the area and arc length of the curved shear zone boundary. The area and arc length were calculated by the curve function of the boundary, which is firstly predicted by FEM simulation. Then, an experimental device was set up to carry out the broaching experiment with straight profile tools and complex profile tools in accordance with the progressive depth of the cut. Based on the experiments, the traditional broaching model and the modified model with the complex profile tool have been established. Compared with the traditional force model, the accuracy of the modified model has been moderately improved. Furthermore, the modified main broaching force (Y direction) model and the normal force (Z direction) model show a significant improvement in accuracy of 4.8% and 9.7%, respectively, which suggests that the projection area of curved shear zone A1 and the projection arc length of curved shear zone l1 have a big impact on the broaching process. It is firmly believed that the modified model proposed in this paper can provide guidance for the design of complex profile tools and facilitate the efficient and high-precision machining of complex parts. [ABSTRACT FROM AUTHOR]

This paper studied the effect of graphene additive on the lubricating capacity of vegetable oils. The castor oil, rapeseed oil, and corn oil were chosen as base oils, and ultrasonic agitation was used to prepare the graphene in vegetable oil suspensions with six different mass fractions. These suspensions were utilized as minimum quantity lubrication (MQL) lubricants during the internal tapping process of ADC12 aluminum alloy. Tapping torque and thread surface morphology analyses were applied to evaluate the lubrication performance. The results showed that the pure castor oil MQL achieves the lowest average tapping torque in all the base oils. Meanwhile, the use of graphene additive can significantly reduce the tapping torque, and this torque reduction shows a nonlinear relationship with the graphene mass fraction. As an overall trend, the 0.5% mass fraction is the optimum concentration, which decreased the average torque by 0.64 Nm (11.4%), 1.6 Nm (16.4%), and 1.7 Nm (17.7%) compared with pure castor oil, rapeseed oil, and corn oil, respectively. Moreover, the scratching defects on the thread surface were obviously reduced with the application of graphene additive. This torque-reducing and anti-wear effect could be related with the graphene-related friction films formed on the metal surfaces. The research verified that the vegetable oil-based graphene suspension can be used as a substitute for the conventional mineral oil-based metalworking fluids. [ABSTRACT FROM AUTHOR]

Broaching is widely used in the aerospace field owing to its high efficiency and heavy load. However, heavy-load cutting causes intense squeezing and friction in the tool-chip contact area, resulting in a lack of lubrication. Therefore, three textures (i.e., micro-pit, stripe, mesh) are prepared on the rake face of broaching tool with a laser processing technique to improve cutting performance. Afterward, textures are covered with copper using the reciprocating rotational friction to enhance the wettability and heat dissipation capacity of the broaching tool. Experiments approve that striped textures covered with copper reduce the cutting force by 14.6% and the cutting temperature decreases from 90.13 to 76.9 ℃, compared with non-textured cutting teeth. Obtained results indicate that the wettability of cutting fluid on the tool surface is significantly improved due to the capillary force of micro-pores generated by the copper covering, especially in the direction to the cutting edge. Furthermore, the copper debris absorbs heat quickly in the cutting areas and is subsequently taken away by chips and cutting fluids, thereby reducing the cutting temperature. [ABSTRACT FROM AUTHOR]

The last decade has witnessed an explosion of interest in the cutting load analysis for multifarious tools, especially in experiments and classical 2D model. But the cutting load model for broaching tool with grooves is still not clear and functional. In this paper, a new cutting load model applied to the broaching tool, which has some grooves on the flank face of the tooth, is reported. The model takes account of the load reduction effect of grooves on the tool teeth and the load strengthening effect of the bumps on the workpiece. Then, based on the new model, the cutting load simulation analyses for 5 different types of broaching tools are presented and compared with the corresponding experimental results. The results show that cutting load can be well assessed with the proposed new model. And an interesting phenomenon is found that the grooves on the tool teeth are not the more, the better. Among the 5 different types of broaching tools researched, 4/5 type broaching tool shows the best cutting performance. [ABSTRACT FROM AUTHOR]